User Raff.Edward

22 votes

Accepted

Why Adaboost with Decision Trees?

answered Nov 21, 2014 at 1:13

17 votes

Accepted

Can Random Forests do much better than the 2.8% test error on MNIST?

answered Dec 7, 2013 at 17:38

8 votes

Accepted

How to handle unseen features in a Naive Bayes classifier?

answered Jul 20, 2014 at 19:43

7 votes

Accepted

Interpretating the C value in a linear SVM

answered Jul 20, 2014 at 22:15

5 votes

At what point does LDA (Latent Dirichlet Allocation) not make sense to use?

answered Dec 8, 2013 at 17:44

4 votes

Kernel SVM on sparse data

answered Dec 4, 2014 at 5:24

4 votes

How to get probability from the confidence score in SVM

answered Jul 27, 2015 at 3:52

3 votes

Accepted

neural network output layer for binary classification

answered Jun 1, 2014 at 22:57

2 votes

Regression Trees / Boosted Regression Trees for Tweedie Distribution in R

answered May 26, 2014 at 19:22

2 votes

How is the training set constructed for multi-class SVMs?

answered Jun 1, 2014 at 4:02

2 votes

Decision tree with equal points

answered Sep 30, 2015 at 17:06

2 votes

Machine Learning to Predict Class Probabilities

answered Nov 16, 2013 at 0:39

1 vote

Regression Tree with nested factors

answered Nov 16, 2013 at 1:52

1 vote

Modifying decision function in LibSVM

answered Nov 30, 2013 at 4:38

1 vote

How to compare two clusterings generated by two clustering approaches

answered Sep 1, 2014 at 15:58

1 vote

Accepted

Theoretical error bounds of classification and regression trees

answered Dec 27, 2013 at 8:00

1 vote

Accepted

Bayesian Classification evaluation

answered Jan 8, 2014 at 23:37

1 vote

Offline training or batch wise training

answered Mar 26, 2014 at 3:40

1 vote

Can adaboost choose the same variable for multiple splits for a given tree?

answered Sep 19, 2014 at 23:09

1 vote

Accepted

deciding between classification and regression in random forest

answered Sep 29, 2015 at 4:32

1 vote

Practical ways to deal with a large number of variables

answered Sep 29, 2015 at 4:39

0 votes

ML & AI - Algorithm recommendation for "optimization by tuning parameters"?

answered Jun 1, 2014 at 22:53

0 votes

Latent Dirichlet Allocation as input for WEKA

answered Apr 15, 2014 at 3:08

0 votes

Accepted

How to determine the best split threshold (split point) in Hoeffding tree (for continuous attributes)?

answered Sep 2, 2014 at 23:55

0 votes

Regression problem with "included classification"

answered Dec 17, 2013 at 4:57

0 votes

improve precision in text classification

answered Dec 17, 2013 at 5:04

-1 votes

Applying kernel function to input data before giving it to algorithm

answered Nov 16, 2013 at 0:52

Stack Exchange Network

27 Answers

Why Adaboost with Decision Trees?

Can Random Forests do much better than the 2.8% test error on MNIST?

How to handle unseen features in a Naive Bayes classifier?

Interpretating the C value in a linear SVM

At what point does LDA (Latent Dirichlet Allocation) not make sense to use?

Kernel SVM on sparse data

How to get probability from the confidence score in SVM

neural network output layer for binary classification

Regression Trees / Boosted Regression Trees for Tweedie Distribution in R

How is the training set constructed for multi-class SVMs?

Decision tree with equal points

Machine Learning to Predict Class Probabilities

Regression Tree with nested factors

Modifying decision function in LibSVM

How to compare two clusterings generated by two clustering approaches

Theoretical error bounds of classification and regression trees

Bayesian Classification evaluation

Offline training or batch wise training

Can adaboost choose the same variable for multiple splits for a given tree?

deciding between classification and regression in random forest

Practical ways to deal with a large number of variables

ML & AI - Algorithm recommendation for "optimization by tuning parameters"?

Latent Dirichlet Allocation as input for WEKA

How to determine the best split threshold (split point) in Hoeffding tree (for continuous attributes)?

Regression problem with "included classification"

improve precision in text classification

Applying kernel function to input data before giving it to algorithm